An AI model is capable of predicting the risk of a thousand diseases

This research looks to be a significant step towards scalable, interpretable, and – most importantly – ethically responsible form of predictive modelling in medicine. The clear demonstration of how explainable AI can be used to model predictions is crucial if this technology is to be utilised in clinical practices, and suggests it may be possible to identify high risk individuals in need of intervention. 

While the current version relies solely on anonymized clinical records, it’s encouraging to see that the model architecture has been deliberately designed to accommodate richer data types, such as biomarkers, imaging, and even genomics. With these future integrations, the Delphi platform is well-positioned to evolve into a truly multimodal, precision-medicine tool.

The authors have developed an AI model that is capable of accurately predicting disease and have shown that it works on data from the UK BioBank as well as nearly 2m people from Denmark. However, this is still a long way from improved healthcare as the authors acknowledge that both datasets are biased in terms of age, ethnicity, and current healthcare outcomes. While improved risk scores and the potential for precision medicine is an interesting future goal, the immediate challenge for healthcare is to ensure there is a sufficient digital infrastructure and skills base for everyone, regardless of socio-economic background, so the currently available technologies can be offered to those who most need improved access to treatments.